Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1720 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.9421. Min Range: -5.9421

Max Act: 5.9421. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 5.9421. Min Range: -5.9421

Max Act: 5.5401. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 5.9421. Min Range: -5.9421

Max Act: 5.7845. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 5.9421. Min Range: -5.9421

Max Act: 4.2720. Min Act: -0.0000

Data Index: 105041 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 5.9421. Min Range: -5.9421

Max Act: 4.3147. Min Act: -0.0000

Data Index: 255911 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.9400. Min Act: -0.0000

Data Index: 718800 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 5.9421. Min Range: -5.9421

Max Act: 4.1087. Min Act: -0.0000

Data Index: 309977 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 5.9421. Min Range: -5.9421

Max Act: 4.0746. Min Act: -0.0000

Data Index: 94864 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8943. Min Act: -0.0000

Data Index: 195278 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8411. Min Act: -0.0000

Data Index: 914400 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.9798. Min Act: -0.0000

Data Index: 667192 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.9093. Min Act: -0.0000

Data Index: 56106 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.7180. Min Act: -0.0000

Data Index: 80945 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.9276. Min Act: -0.0000

Data Index: 528352 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8766. Min Act: -0.0000

Data Index: 1252951 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8479. Min Act: -0.0000

Data Index: 797853 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.6739. Min Act: -0.0000

Data Index: 58458 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8176. Min Act: -0.0000

Data Index: 49650 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.8057. Min Act: -0.0000

Data Index: 1079294 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 5.9421. Min Range: -5.9421

Max Act: 3.7503. Min Act: -0.0000

Data Index: 173801 (C4 (Web Text))

Max Activating Token Index: 341